Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76597
    Prev
    Next
    INDEX
    Explanations

    references to technological systems and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idth
    -0.08
    nga
    -0.07
    æ³³
    -0.07
    xac
    -0.06
    iche
    -0.06
    _pull
    -0.06
     iddi
    -0.06
     Fiber
    -0.06
    adx
    -0.06
    dbus
    -0.06
    POSITIVE LOGITS
     altogether
    0.08
    inz
    0.06
    astle
    0.06
    irate
    0.06
    rangle
    0.06
    utow
    0.06
    inions
    0.06
     tilt
    0.06
    ropa
    0.06
     Leer
    0.06
    Activations Density 0.005%

    No Known Activations